Lucas, C., Bihani, A., Kukka, R., Tsai, C.-H., Sarker, J., & Imran, M. M. (2026) — University of Nebraska at Omaha, Penn State. arXiv preprint.
📄 Full text (arXiv)
Key Finding
Socratic questioning, reflection prompts, misconception checks, and mandatory pauses produce better K-12 engagement than directive answer-giving AI tutors.Synthesis
SocratiCode demonstrates a participatory design evolution from directive AI tutor to Socratic learning companion for K-12 programming. Over four weeks with two Python learners, the system shifted from flexible tutorial generation toward dialogic support: guided questioning instead of answers, reflection prompts, misconception checks, incremental hints, and mandatory pauses requiring learner input. This Socratic shift improved explanation clarity and problem-solving engagement. The findings directly reinforce the codify-socratic-tutoring-programming approach of discovery-based learning over direct answer generation, but extend it to the K-12 context where cognitive-load-theory concerns are particularly acute. The emphasis on mandatory pauses and reflection aligns with metacognition and self-regulated-learning scaffolding strategies. The authors argue that AI tutoring is most effective as a companion within a human-guided framework, not an answer engine — a principle that resonates with the human-in-the-loop-ai architecture and the findings from structured-llm-feedback-programming that less guided feedback may be more effective.Related Pages